Explain LCP

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint and openWorldHint annotations, it discloses operational traits: one Chrome UX Report call, no Lighthouse runs, no noise to average away, and it requires an API key and real-user data. It also surfaces two crucial caveats that affect interpretation of results: phases are separate 75th percentiles and do not sum to LCP, and they are measured only over image-LCP visits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The definition is front-loaded with when to use it and which siblings to prefer, followed by method and caveats. It is dense but the caveats about phase summing and image-only measurement earn their place; only the extended measured-gap example is slightly verbose relative to the core instruction.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex diagnostic tool with no output schema, the description explains what is returned: the four phase breakdown, phase shares, and the image share. It also covers important prerequisites (API key, real-user data) and interpretation limits, leaving no major gap for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has only one parameter ('urls') and 100% schema description coverage, so the schema already explains that it accepts absolute http(s) URLs and defaults to saved URLs. The description adds no further parameter-specific meaning such as batching behavior or URL-list limits, so the baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: it breaks a slow LCP into four named phases (server response, image fetch delay, download, paint delay). It explicitly distinguishes itself from get_field_data (LCP figure alone) and analyse_page (lab scores and fixes), so an agent can identify when this tool applies.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives an explicit trigger: 'Use when Largest Contentful Paint is the problem, to find which part of the load owns it.' It names two alternatives and the precise conditions that route to them: get_field_data for the LCP figure alone, and analyse_page for lab scores and what to fix.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.